© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 3482
    Prev
    Next
    INDEX
    Explanations

    code related terms such as function names, variables and transformation instructions

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and concepts related to 3D modeling and rendering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olics
    -0.84
    zek
    -0.77
    esson
    -0.70
    Trust
    -0.70
    judicial
    -0.69
    issued
    -0.69
    icrobial
    -0.69
    untu
    -0.68
    gew
    -0.67
    rists
    -0.67
    POSITIVE LOGITS
     Texture
    0.94
     Painter
    0.88
     sprite
    0.83
     cursor
    0.81
     coordinates
    0.78
    map
    0.78
     texture
    0.77
     Distance
    0.76
     Width
    0.76
     textures
    0.76
    Activations Density 0.345%

    No Known Activations